Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He ran his hand over the perfectly aligned rows of orchids in his greenhouse. The intricate patterns of color on the petals, a consequence of his Chromatic Anomaly, were a source of fascination and, he freely admitted to himself, delight. His orchids had won every local competition for the past five years.

He heard a knock at the greenhouse door. It was Mrs. Peterson, a woman he knew as a quiet observer who took an interest in his flowers. “Mr. Davies,” she said, her voice unusually hesitant. “I… I think I know what you have.”

He straightened, a small smile playing on his lips. “Oh?” he asked, genuinely curious.

Mrs. Peterson held out her hand, revealing a vibrant, almost luminescent, patch of skin discoloration. “Chromatic Anomaly. I’ve had it since I was a child. Your flowers... They inspired me." A small blush rose to her cheeks. He felt a wave of warmth.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion proud. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 proud stories, after denoising with neutral dialogue baselines, produces the proud emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the proud vector is projected through the unembedding matrix.

Promoted:
de0.514
la0.457
😎0.400
happy0.394
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453